Unverified50% confidenceEventExact time
本次测试选取了五款AI模型：DeepSeek R1、Claude Sonnet 3.7、ChatGPT o3 Mini、Grok 3、通义千问2.5 Max，通过统一提示词让它们各自生成可运行的网页版贪吃蛇游戏
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
五大AI模型做游戏实测对比：零基础编程谁最强
bilibiliso-PHI-a_903/1/2025
Related Claims
Unverified在图片隐藏虫子识别测试中，Sonnet 5的Max模式花费约10分钟并识别结果完全正确，而Gemini顶配模型只找到4只，GPT-5.5 X-High未能检测出66% similarUnverified在简单题中，GLM 5.1补了19行测试，Kimi K2.6补了12行，其他五个模型（包括Sonnet 4.6）一行测试都没写66% similarUnverifiedV4 Pro Max满血推理模式下算法竞赛3206分、编程93.5分、科学问答90.1分、软件工程80.6分、终端操作67.9分65% similarUnverifiedGLM4在World of AI基准测试工具中排名第五64% similarUnverified参与测试的四款模型是QDAM 3.7 Plus、LongCat 2.0、DeepSeek Feast Pro和MiniMax Mi364% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/60451API
curl https://kongchang.com/api/v1/knowledge/claims/60451MCP
get_claim(id=60451)